WO2019214336A1

WO2019214336A1 - Content pushing method and apparatus, and machine readable storage medium

Info

Publication number: WO2019214336A1
Application number: PCT/CN2019/077556
Authority: WO
Inventors: 王冉; 李东军; 黄宇; 陈颖祥; 乐诚; 孙雨田; 张颖; 杨楠楠; 赵延亮; 王风雷
Original assignee: 苏州跃盟信息科技有限公司
Priority date: 2018-05-10
Filing date: 2019-03-08
Publication date: 2019-11-14
Also published as: CN108681919A; JP2020536294A

Abstract

A content pushing method and apparatus, and a machine readable storage medium. The method comprises: receiving feedback information sent by a terminal when a first user reads content, the feedback information comprising positive feedback information and negative feedback information (S201); correcting the positive feedback information and the negative feedback information, analyzing the corrected positive feedback information and negative feedback information, and updating an interest tag of the first user stored in a first user information database (S202); after receiving an advertisement recommendation request sent by the terminal, obtaining content data associated with the interest tag of the user based on the interest tag of the user, and recommending the content data to the first user (S203). According to the method, the content in which the user is interested can be obtained according to a real-time interest of the user, accurate recommendation to the user is achieved, and the efficiency of advertising is improved.

Description

Content push method, device and machine readable storage medium

Cross-reference to related applications

The present disclosure claims priority to Chinese Patent Application No. 2018104451287, filed on May 10, 2018, which is incorporated herein by reference.

Technical field

The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, and a machine readable storage medium for pushing content.

Background technique

In the prior art, when an advertiser pushes an advertisement, the advertiser's interest is considered, and the relevant advertisement information is pushed to the user according to the user's interest; the inventor finds in the research that the prior art is based on the user's interest. When the information is pushed by the advertisement, the factor of the user's non-interest information is not fully considered, and the pushed advertisement cannot be more accurately matched with the user's intention at the time. At this time, the pushed advertisement may cause harassment to the user and reduce The effectiveness of advertising.

Summary of the invention

In view of this, one of the purposes of the present disclosure is to provide a method, apparatus, and machine readable storage medium for content push to more accurately push content of interest to a user to a user.

In a first aspect, an embodiment of the present disclosure provides a content pushing method, where the method includes:

Receiving feedback information of the first user when the content is read by the terminal, where the feedback information includes positive feedback information and negative feedback information;

Correcting the positive feedback information and the negative feedback information, analyzing the corrected positive feedback information and negative feedback information, and updating the interest tag of the first user stored in the first user information database;

After receiving the advertisement recommendation request sent by the terminal, acquiring content data associated with the interest tag of the first user based on the interest tag of the first user, and recommending the content data to the first user.

Optionally, in the above method, the positive feedback information and the negative feedback information are corrected, and the corrected positive feedback information and negative feedback information are analyzed, and the first stored in the first user information database is updated. The steps of a user's interest tag include:

The first user's interest tag stored in the first user information database is updated in real time according to the received positive feedback information and negative feedback information.

Optionally, in the foregoing method, the correcting the positive feedback information and the negative feedback information, including:

The positive feedback information and the negative feedback information are respectively corrected based on a negative correlation of the positive feedback information and the negative feedback information.

Semantic analysis of the positive feedback information, obtaining a user's interest keyword, and storing the interest keyword in the first user information database as an interest tag of the first user; performing the negative feedback information Semantic analysis, obtaining keywords corresponding to the negative feedback information;

Modifying or deleting the keyword as the interest tag of the first user according to the correlation between the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information.

Optionally, in the foregoing method, the correlation between the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information is modified or deleted as a key of the first user's interest tag. The steps of the word include:

Determining a semantic inclusion relationship of a keyword corresponding to the positive feedback information and a keyword corresponding to the negative feedback information;

Determining a range of things of interest to the user according to a semantic inclusion relationship of the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information, and modifying or deleting a keyword that is an interest tag of the first user.

Optionally, in the above method, the positive feedback information includes: a first user's reading content, a favorite content, a copy content, a search content, a forwarding content, and information about purchasing a product related to the content.

Optionally, in the foregoing method, the positive feedback information further includes: information used to represent a positive emotion of the first user.

Optionally, in the above method, the negative feedback information includes: first-time household report content, closed content, and content marked as not interested.

Optionally, in the above method, the negative feedback information further includes: information used to represent a negative emotion of the first user.

Optionally, in the foregoing method, the method further includes: acquiring an interest tag of a second user related to the first user, and updating the interest tag of the first user based on the interest tag of the second user.

A content pushing method provided by an embodiment of the present disclosure has at least the following positive effects: positive feedback information and negative feedback information sent by the acquired terminal, and the positive feedback information and the negative feedback information are corrected, according to the corrected The positive feedback information and the negative feedback information are used to update the interest tag of the first user stored in the information database; and after receiving the advertisement recommendation request sent by the terminal, the third user is recommended to be associated with the interest tag according to the interest tag of the first user. The content can further obtain the content that the user is interested in according to the real-time interest of the user, and perform the current user recommendation, thereby improving the efficiency of the advertisement delivery and improving the effectiveness of the advertisement.

In a second aspect, the embodiment of the present disclosure further provides a content pushing device, where the device includes:

a receiving module, configured to receive feedback information of the first user when the content is read by the terminal, where the feedback information includes positive feedback information and negative feedback information;

a first update module, configured to modify the positive feedback information and the negative feedback information, analyze the corrected positive feedback information and negative feedback information, and update the interest of the first user stored in the first user information database label;

And a recommendation module, configured to: after receiving the advertisement recommendation request sent by the terminal, acquire content data associated with the user's interest tag based on the user's interest tag, and recommend the content data to the first user.

Optionally, in the foregoing apparatus, the first update module is specifically configured to: perform real-time correction according to the received positive feedback information and negative feedback information, and update an interest of the first user stored in the first user information database. label.

Optionally, in the foregoing apparatus, the first update module includes: a correction unit, configured to perform the positive feedback information and the negative feedback information based on a negative correlation between the positive feedback information and the negative feedback information Make corrections.

Optionally, in the foregoing apparatus, the first update module is specifically configured to perform semantic analysis on the positive feedback information, obtain a user's interest keyword, and store the interest keyword in the first user information database. And performing the semantic analysis on the negative feedback information to obtain a keyword corresponding to the negative feedback information; and corresponding to the keyword corresponding to the positive feedback information and the negative feedback information The correlation between the keywords modifies or deletes the keyword as the interest tag of the first user.

Optionally, in the foregoing apparatus, the first update module is modified or deleted according to a correlation between a keyword corresponding to the positive feedback information and a keyword corresponding to the negative feedback information as the first user a keyword of the interest tag, determining a semantic inclusion relationship of the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information, and according to the keyword corresponding to the positive feedback information and the negative feedback information The semantic inclusion relationship of the corresponding keyword re-determines the range of things that the user is interested in, and modifies or deletes the keyword that is the interest tag of the first user.

Optionally, in the foregoing apparatus, the device further includes: a second update module, configured to acquire an interest tag of a second user related to the first user, and update the identifier according to the interest tag of the second user The first user's interest tag.

In a third aspect, an embodiment of the present disclosure provides a machine readable storage medium storing instructions executable by a processor, the instructions being implemented by a processor to implement the content recommendation method provided by an embodiment of the present disclosure.

A content pushing apparatus provided by an embodiment of the present disclosure has at least the following positive effects: positive feedback information and negative feedback information sent by the acquired terminal, and the positive feedback information and the negative feedback information are corrected, according to the corrected The positive feedback information and the negative feedback information are used to update the interest tag of the first user stored in the information database; and after receiving the advertisement recommendation request sent by the terminal, the third user is recommended to be associated with the interest tag according to the interest tag of the first user. The content can further obtain the content that the user is interested in according to the real-time interest of the user, thereby accurately recommending to the user, improving the efficiency of advertising, and improving the effectiveness of the advertisement.

The above described objects, features, and advantages of the present invention will become more apparent from the description of the appended claims.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings to be used in the embodiments will be briefly described below. It should be understood that the following drawings show only certain embodiments of the present disclosure, and thus It should be seen as a limitation on the scope, and those skilled in the art can obtain other related drawings according to these drawings without any creative work.

FIG. 1 is a schematic diagram of an application scenario of a content pushing method according to an embodiment of the present disclosure;

FIG. 2 is a schematic flowchart diagram of a content pushing method according to an embodiment of the present disclosure;

FIG. 3 is a schematic flowchart diagram of another content pushing method according to another embodiment of the present disclosure;

FIG. 4 is a schematic structural diagram of a content pushing apparatus according to an embodiment of the present disclosure;

FIG. 5 is a schematic structural diagram of another content pushing apparatus according to an embodiment of the present disclosure;

FIG. 6 is a schematic structural diagram of a server according to an embodiment of the present disclosure.

detailed description

The technical solutions in the embodiments of the present disclosure will be clearly and completely described in conjunction with the drawings in the embodiments of the present disclosure. It is a partial embodiment of the present disclosure, and not all of the embodiments. The components of the disclosed embodiments, which are generally described and illustrated in the figures herein, can be arranged and designed in various different configurations. The detailed description of the embodiments of the present disclosure, which is set forth in the claims All other embodiments obtained by a person skilled in the art based on the embodiments of the present disclosure without creative efforts are within the scope of the present disclosure.

It is considered that the prior art does not take into account the real-time interest of the user in the advertisement push, which in turn causes the advertisement to be disturbed to the user, thereby reducing the benefit of the advertisement; based on this, the embodiment of the present disclosure provides a content. The pushing method and apparatus are described below by way of examples.

Referring to FIG. 1, the solution is applicable to an application scenario in which the terminal 101 interacts with the server 102. The terminal 101 and the server 102 can establish a communication connection, and the terminal 101 and the server 102 can perform data communication after establishing a communication connection.

The terminal 101 described above may be a mobile phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server 102 described above is capable of responding to a request sent by the terminal.

Referring to the embodiment shown in FIG. 2, a method for content push is provided in the embodiment of the present disclosure, and the method includes the following steps:

S201. The feedback information sent by the first user when the content is read by the receiving terminal, where the feedback information includes positive feedback information and negative feedback information.

When the user opens a certain webpage for content reading, the terminal acquires the operation information or the reading content of the user, and the terminal feeds back the operation information or the reading content to the server in real time; the operation information or the reading content constitutes the above Positive feedback information and negative feedback information.

Specifically, the foregoing positive feedback information may include: a user's reading content, a favorite content, a copy content, a search content, a forwarding content, and information about a product purchased by the user related to the content; and the server receives the above positive feedback information sent by the terminal. In the following, the positive feedback information may be semantically analyzed, and the user's interest keyword is determined according to the result obtained by the semantic analysis, and the interest keyword is stored in the first user information database, and the interest keyword constitutes the first A user's interest tag.

Specifically, the negative feedback information includes: reporting content of the first user, closing content, marking the content as not interested, selecting content that is no longer reminded, and the like.

The positive feedback information may further include: information for indicating a positive emotion of the first user; the information may be derived by a pre-specified reading behavior of a user capable of reflecting the user's emotion, and the user's reading behavior is, for example, It may be the speed of dragging the progress bar, the frequency of the mouse click, etc., when the speed of dragging the progress bar is less than the first set value, and the frequency of the mouse click is less than the first preset value, the probability that the user's emotion is a positive emotion at this time Larger, positive feedback information may include information such as "positive emotions"; when the user drags the progress bar faster than the first set value, and the click frequency of the mouse is greater than the first set value, the user's The probability that the emotion is negative emotion is large. At this time, the negative feedback information may include information such as “negative emotion”, and when the server receives the information that “negative emotion” is included in the negative feedback information, the setting is made to reduce the advertisement push by the server. The frequency; thereby improving the user experience.

S202. Correct the positive feedback information and the negative feedback information, analyze the corrected positive feedback information and the negative feedback information, and update the interest tag of the first user stored in the first user information database.

The terminal collects the above positive feedback information and negative feedback information in real time, and sends the positive feedback information and the negative feedback information to the server. After the server receives the positive feedback information and the negative feedback information, the server separately receives the positive feedback information and the negative feedback information. Semantic analysis is performed to obtain keywords corresponding to positive feedback information and keywords corresponding to negative feedback information, and user behavior matching is performed according to keywords corresponding to the positive feedback information and keywords corresponding to negative feedback information, and finally the user's interest keywords are obtained. The interest keyword is stored in the first user information database, and the interest keyword is used as the interest tag of the user, that is, the interest tag of the first user stored in the information database of the first user is updated. Each of the users corresponds to an information database, and each information database stores an interest tag corresponding to the user.

Performing the user behavior matching according to the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information may include: performing the positive feedback information and the negative based on the negative correlation between the positive feedback information and the negative feedback information. Feedback information is corrected. The modified manner may include modifying or deleting a keyword that is an interest tag of the first user according to a correlation between a keyword corresponding to the positive feedback information and a keyword corresponding to the negative feedback information.

Specifically, the server may determine a semantic inclusion relationship of the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information. Then, according to the semantic inclusion relationship of the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information, the range of things of interest to the user is re-determined, and the keyword that is the interest tag of the first user is modified or deleted.

For example, when the positive feedback information of the user received by the server includes the advertisement information that concerns the automobile, but the negative feedback information of the user further includes: the information of the advertisement related to the used car is closed, then the new feedback information may be added to the new vehicle. Relevant advertising information, at this time, utilizes the negative correlation between positive feedback information and negative feedback information. For another example, when the user's negative feedback information includes: an advertisement that closes the middle school counseling course continuously for more than a preset number of times, whether the search in the positive feedback information includes the advertisement of the middle school counseling course, and if yes, the positive feedback Deleted from the message. It can be seen that the positive feedback information and the negative feedback information may be the number of times that the user has certain operational actions.

In this embodiment, the first user interest tag is adjusted by determining a semantic inclusion relationship of the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information, and determining the interest by using only the frequency of occurrence or the weight of the keyword. The way tags are used to determine the user's range of interest more quickly and accurately provides data support for accurate content push.

Since the user's interest is constantly changing, the user is interested in one thing for a period of time, and may be interested in another thing in another time period; in this embodiment, the timeliness of the user's interest is fully considered. The real-time correction of the positive feedback information and the negative feedback information sent by the terminal or the correction of the preset time period may ensure that the content data recommended to the user is currently of interest to the user, and the content data herein may refer to the advertisement. , articles, etc., if it is an advertisement, it can improve the effectiveness of advertising.

Exemplarily, the advertisement recommendation request includes a user identifier, and the user identifier may be a username or a terminal hardware identifier or an IP address of the login application. If the terminal sends an advertisement recommendation request through the social network application, the terminal automatically obtains the currently logged-in user name, generates an advertisement recommendation request and sends the advertisement recommendation request to the server, and the server determines the user by using the user name included in the advertisement recommendation request. For the advertisement recommendation request sent when the application is not logged in, the terminal hardware identifier or IP address may be used to identify the user's information, and the server determines the user by using the hardware identifier or IP address included in the advertisement recommendation request.

S203. After receiving the advertisement recommendation request sent by the terminal, acquire content data associated with the user's interest tag based on the user's interest tag, and recommend the content data to the first user.

The setting may be such that when the terminal detects that the user opens the webpage, or detects that the user inputs the search content in the search box, the terminal generates an advertisement recommendation request, and the terminal sends the advertisement recommendation request to the server, and the server receives the advertisement recommendation request, and acquires the advertisement recommendation request. The content data associated with the interest tag and recommend the content data to the user; the content data may be content such as an advertisement or an article.

After receiving the advertisement data sent by the server, the terminal displays the advertisement data in a specific advertisement recommendation area, or displays the scrolling scroll in the search box, or is arranged in a drop-down box below the search box, because When the user browses the webpage, the first area to be looked at is the position of the search box, which not only improves the utilization efficiency of the webpage layout but also the exposure rate of the advertisement.

In this embodiment, in the case of an advertisement, the advertisement data is stored in the advertisement pool, and each advertisement is preset with a plurality of labels, for example, an advertisement of a children's shirt, and the corresponding label may be “children's clothes” and “tops”. a "boy" or the like; the server automatically matches the advertisement data associated with the interest tag from the advertisement pool according to the user's interest tag, where the associated advertisement data may include: the advertisement tag is consistent with the user's interest keyword Advertising data related to the user's keyword.

The server may further calculate the degree of association between the matched advertisement data and the user's interest keywords, and sort according to the degree of association, and sequentially recommend the advertisement data to the user according to the order of relevance.

In still another embodiment of the present application, the foregoing content pushing method further includes the following steps:

S204. Acquire an interest tag of the second user related to the first user, and update the interest tag of the first user based on the interest tag of the second user.

After updating the user's interest tag according to the corrected positive feedback information and the negative feedback information of the first user, the server acquires the interest tag of the second user related to the first user again, and further updates the second user according to the interest tag of the second user. A user's interest tag.

The second user associated with the first user may be a user whose search path entered in the preset time period is consistent with the search path of the first user or whose coincidence exceeds a preset threshold.

The first user and the second user may have the same or similar interests. Therefore, in this embodiment, the interest tag of the first user is updated according to the interest tag of the second user. To some extent, the range of interest of the first user is predicted according to the range of interest of the second user, thereby pushing similar content for the first user.

It can be seen that the terminal is further configured to: when the user performs information retrieval, obtain a retrieval path input by the user, and send the retrieval path to the server, and the server receives and stores the retrieval path of the user.

In still another embodiment of the present disclosure, a content pushing device is disclosed, the device comprising:

The receiving module 301 is configured to receive feedback information of the first user when the content is read by the terminal, where the feedback information includes positive feedback information and negative feedback information;

The first update module 302 is configured to modify the positive feedback information and the negative feedback information, analyze the corrected positive feedback information and negative feedback information, and update the first user stored in the first user information database. Interest tag

The recommendation module 303 is configured to: after receiving the advertisement recommendation request sent by the terminal, acquire content data associated with the interest tag of the user based on the interest tag of the user, and recommend the content data to the first user.

Preferably, the first update mode 302 block includes: a correction unit, configured to perform correction on the positive feedback information and the negative feedback information based on the negative correlation between the positive feedback information and the negative feedback information.

Preferably, referring to the embodiment shown in FIG. 5, the foregoing apparatus further includes:

The second update module 304 is configured to acquire an interest tag of the second user related to the first user, and update the interest tag of the first user based on the interest tag of the second user.

A non-volatile computer storage medium is also provided in an embodiment of the present disclosure, the computer storage medium storing computer executable instructions that can perform the content push method in any of the above method embodiments.

As shown in FIG. 6 , a schematic diagram of a server 102 according to another embodiment of the present disclosure includes a processor 401 , a memory 402 (machine readable storage medium), and a bus 403 . And, the memory 402 stores the machine executable instructions, and by reading and executing the machine executable instructions in the memory 402 corresponding to the content push logic, the processor 401 can perform the content push method described above.

For example, the memory 403 stores execution instructions. When the device is running, the processor 401 communicates with the memory 402 via the bus 403. The processor 401 executes the following execution instructions stored in the memory 402: the first user sent by the receiving terminal reads the content. Feedback information, the feedback information includes positive feedback information and negative feedback information;

After receiving the advertisement recommendation request sent by the terminal, the content data associated with the user's interest tag is acquired based on the user's interest tag, and the content data is recommended to the first user.

The processor 401 is specifically configured to:

The positive feedback information and the negative feedback information are corrected based on a negative correlation of the positive feedback information and the negative feedback information.

And acquiring an interest tag of the second user related to the first user, and updating the interest tag of the first user based on the interest tag of the second user.

The memory 402 referred to herein may be any electronic, magnetic, optical, or other physical storage device that may contain or store information such as executable instructions, data, and the like. For example, the machine-readable storage medium may be: RAM (Radom Access Memory), volatile memory, non-volatile memory, flash memory, storage drive (such as a hard disk drive), solid state drive, any type of storage disk. (such as a disc, dvd, etc.), or a similar storage medium, or a combination thereof.

The computer program product for performing the content push method provided by the embodiment of the present disclosure includes a computer readable storage medium storing program code, and the program code includes instructions for executing the method described in the foregoing method embodiment, and the specific implementation Refer to the method embodiment, and details are not described herein again.

The device for content push provided by the embodiments of the present disclosure may be specific hardware on the device or software or firmware installed on the device. The implementation principle and the technical effects of the device provided by the embodiments of the present disclosure are the same as those of the foregoing method embodiments. For a brief description, where the device embodiment is not mentioned, reference may be made to the corresponding content in the foregoing method embodiments. A person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working processes of the foregoing system, the device and the unit can refer to the corresponding processes in the foregoing method embodiments, and details are not described herein again.

In the embodiments provided by the present disclosure, it should be understood that the disclosed apparatus and method may be implemented in other manners. The device embodiments described above are merely illustrative. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some communication interface, device or unit, and may be electrical, mechanical or otherwise.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in the embodiment provided by the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

The functions may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product. Based on such understanding, the portion of the technical solution of the present disclosure that contributes in essence or to the prior art or the portion of the technical solution may be embodied in the form of a software product stored in a storage medium, including The instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present disclosure. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

It should be noted that similar reference numerals and letters indicate similar items in the following figures. Therefore, once an item is defined in a drawing, it is not necessary to further define and explain it in the subsequent drawings. Moreover, the terms "first", "second", "third", and the like are used merely to distinguish a description, and are not to be construed as indicating or implying a relative importance.

It should be noted that the above-mentioned embodiments are merely specific embodiments of the present disclosure, and are used to explain the technical solutions of the present disclosure, and are not limited thereto. The scope of protection of the present disclosure is not limited thereto, although reference is made to the foregoing. The embodiments are described in detail, and those skilled in the art should understand that any one skilled in the art can still modify the technical solutions described in the foregoing embodiments within the technical scope of the disclosure. The changes may be easily conceived, or equivalents may be substituted for some of the technical features. The modifications, variations, and substitutions of the present invention do not depart from the spirit and scope of the technical solutions of the embodiments of the present disclosure. All should be covered by the scope of the disclosure. Therefore, the scope of protection of the present disclosure should be determined by the scope of the claims.

Industrial applicability

The content pushing method, device and machine readable storage medium provided by the embodiment of the present disclosure, the positive feedback information and the negative feedback information sent by the obtained terminal are corrected, and the positive feedback information and the negative feedback information are corrected, according to the modified The positive feedback information and the negative feedback information are used to update the interest tag of the first user stored in the information database; and after receiving the advertisement recommendation request sent by the terminal, recommending to the first user according to the interest tag of the first user The content of the association can further obtain the content that the user is interested in according to the real-time interest of the user, and perform the current user recommendation, thereby improving the efficiency of the advertisement delivery and improving the effectiveness of the advertisement.

Claims

A content pushing method, comprising:

Receiving feedback information of the first user when the content is read by the terminal, where the feedback information includes positive feedback information and negative feedback information;

Correcting the positive feedback information and the negative feedback information, analyzing the corrected positive feedback information and negative feedback information, and updating the interest tag of the first user stored in the first user information database;

After receiving the advertisement recommendation request sent by the terminal, acquiring content data associated with the interest tag of the first user based on the interest tag of the first user, and recommending the content data to the first user.
The method according to claim 1, wherein the positive feedback information and the negative feedback information are corrected, and the corrected positive feedback information and negative feedback information are analyzed, and the first user information database is updated. The steps of storing the first user's interest tag in the middle include:

The first user's interest tag stored in the first user information database is updated in real time according to the received positive feedback information and negative feedback information.
The method according to claim 1 or 2, wherein the correcting the positive feedback information and the negative feedback information comprises:

The positive feedback information and the negative feedback information are respectively corrected based on a negative correlation of the positive feedback information and the negative feedback information.
The method according to claim 1 or 2, wherein the positive feedback information and the negative feedback information are corrected, and the corrected positive feedback information and negative feedback information are analyzed to update the first user. The step of storing the interest tag of the first user in the information database includes:

Semantic analysis of the positive feedback information, obtaining a user's interest keyword, and storing the interest keyword in the first user information database as an interest tag of the first user; performing the negative feedback information Semantic analysis, obtaining keywords corresponding to the negative feedback information;

Modifying or deleting the keyword as the interest tag of the first user according to the correlation between the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information.
The method according to claim 4, wherein the correlation between the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information is modified or deleted as the first user The steps of the keyword of the interest tag include:

Determining a semantic inclusion relationship of a keyword corresponding to the positive feedback information and a keyword corresponding to the negative feedback information;

And according to the keyword corresponding to the positive feedback information and the semantics of the keyword corresponding to the negative feedback information, the relationship includes re-determining the range of things that the user is interested in, and modifying or deleting the keyword that is the interest tag of the first user.
The method according to any one of claims 1 to 5, wherein the positive feedback information comprises: a first user's reading content, a favorite content, a copy content, a search content, a forwarding content, and a purchase related to the content. Product information.
The method according to any one of claims 1-6, wherein the positive feedback information further comprises: information for indicating a positive emotion of the first user.
The method according to any one of claims 1 to 7, wherein the negative feedback information comprises: first-time household report content, closed content, and content marked as not interested.
The method according to any one of claims 1-8, wherein the negative feedback information further comprises: information for indicating a negative emotion of the first user.
The method according to any one of claims 1 to 9, wherein the method further comprises:

Obtaining an interest tag of the second user related to the first user, and updating the interest tag of the first user based on the interest tag of the second user.
A content pushing device, characterized in that the device comprises:

a receiving module, configured to receive feedback information of the first user when the content is read by the terminal, where the feedback information includes positive feedback information and negative feedback information;

a first update module, configured to modify the positive feedback information and the negative feedback information, analyze the corrected positive feedback information and negative feedback information, and update the interest of the first user stored in the first user information database label;

a recommendation module, configured to: after receiving the advertisement recommendation request sent by the terminal, acquire content data associated with the interest tag of the first user based on the interest tag of the first user, and recommend the content data to the first user .
The apparatus according to claim 11, wherein the first update module is configured to perform correction according to the received positive feedback information and negative feedback information in real time, and update the first stored in the first user information database. A user's interest tag.
The apparatus according to claim 11 or 12, wherein the first update module comprises: a correction unit, configured to respectively correct the negative correlation based on the positive feedback information and the negative feedback information Feedback information and negative feedback information are corrected.
The device according to claim 11 or 12, wherein the first update module is specifically configured to perform semantic analysis on the positive feedback information, obtain a user's interest keyword, and store the interest keyword to the location The first user information database is used as the interest tag of the first user; the negative feedback information is semantically analyzed to obtain a keyword corresponding to the negative feedback information; and the keyword and the corresponding information according to the positive feedback information are The correlation between the keywords corresponding to the negative feedback information is modified or deleted as a keyword of the first user's interest tag.
The device according to claim 14, wherein the first update module is modified or deleted according to a correlation between a keyword corresponding to the positive feedback information and a keyword corresponding to the negative feedback information. Determining, according to the keyword of the first user's interest tag, a semantic inclusion relationship of the keyword corresponding to the positive feedback information and the keyword corresponding to the negative feedback information, and according to the keyword and the corresponding information of the positive feedback information The semantic inclusion relationship of the keyword corresponding to the negative feedback information re-determines the range of things that the user is interested in, and modifies or deletes the keyword that is the interest tag of the first user.
The device according to any one of claims 11-15, further comprising:

And a second update module, configured to acquire an interest tag of the second user related to the first user, and update the interest tag of the first user based on the interest tag of the second user.
A machine-readable storage medium, characterized by storing instructions executable by a processor, the instructions, when executed by a processor, implement the content recommendation method of any of claims 1-10.